decoupler.run_aucell
- decoupler.run_aucell(mat, net, source='source', target='target', n_up=None, min_n=5, seed=42, verbose=False, use_raw=True)
AUCell.
AUCell (Aibar et al., 2017) uses the Area Under the Curve (AUC) to calculate whether a set of targets is enriched within the molecular readouts of each sample. To do so, AUCell first ranks the molecular features of each sample from highest to lowest value, resolving ties randomly. Then, an AUC can be calculated using by default the top 5% molecular features in the ranking. Therefore, this metric, aucell_estimate, represents the proportion of abundant molecular features in the target set, and their relative abundance value compared to the other features within the sample.
Aibar S. et al. (2017) Scenic: single-cell regulatory network inference and clustering. Nat. Methods, 14, 1083–1086.
- Parameters:
- matlist, DataFrame or AnnData
List of [features, matrix], dataframe (samples x features) or an AnnData instance.
- netDataFrame
Network in long format.
- sourcestr
Column name in net with source nodes.
- targetstr
Column name in net with target nodes.
- n_upint
Number of top ranked features to select as observed features. If not specified it will be equal to the 5% of the number of features.
- min_nint
Minimum of targets per source. If less, sources are removed.
- seedint
Random seed to use.
- verbosebool
Whether to show progress.
- use_rawbool
Use raw attribute of mat if present.
- estimateDataFrame
AUCell scores. Stored in .obsm[‘aucell_estimate’] if mat is AnnData.